Here, we present a multi-modal deep generative model, the single-cell Multi-View Profiler (scMVP), which is designed for handling sequencing data that simultaneously measure gene expression and chromatin accessibility in the same cell, including SNARE-seq, sci-CAR, Paired-seq, SHARE-seq, and Multiome from 10X Genomics. scMVP generates common latent representations for dimensionality reduction, cell clustering, and developmental trajectory inference and generates separate imputations for differential analysis and cis-regulatory element identification. scMVP can help mitigate data sparsity issues with imputation and accurately identify cell groups for different joint profiling techniques with common latent embedding, and we demonstrate its advantages on several realistic datasets.

Wikipedia is becoming increasingly critical in helping people obtain information and knowledge. Its leading advantage is that users can not only access information but also modify it. However, this presents a challenging issue: how can we measure the quality of a Wikipedia article? The existing approaches assess Wikipedia quality by statistical models or traditional machine learning algorithms. However, their performance is not satisfactory. Moreover, most existing models fail to extract complete information from articles, which degrades the model’s performance. In this article, we first survey related works and summarise a comprehensive feature framework. Then, state-of-the-art deep learning models are introduced and applied to assess Wikipedia quality. Finally, a comparison among deep learning models and traditional machine learning models is conducted to validate the effectiveness of the proposed model. The models are compared extensively in terms of their training and classification performance. Moreover, the importance of each feature and the importance of different feature sets are analysed separately.

We re-examine Tiebout's hypothesis of endogenous sorting in a competitive spatial equilibrium framework, by considering both income and preference heterogeneity and by allowing agents to decide endogenously the number of visits to a 'travel-for' local public good. The equilibrium configuration may be completely segregated, incompletely segregated, or completely integrated, depending on relative market rents and income/preference/local tax parameters. A segregated equilibrium may feature endogenous sorting purely by income or by both income and preferences. While the rich need not be closer to the local public facility site, multiple equilibria may arise when the equilibrium configuration is incompletely segregated. JEL classification: D50, H41Classification par de´placement : biens publics locaux accessibles par de´placement et stratification d'e´quilibre. Les auteurs re´examinent l'hypothe`se de Tiebout de classification endoge`ne dans un cadre d'e´quilibre spatial concurrentiel en tenant compte a`la fois de l'he´te´roge´ne´ite´des revenus et des pre´fe´rences, ainsi qu'en permettant aux agents de de´cider de manie`re endoge`ne du nombre de visites pour se procurer un bien public local par de´placement. Il peut s'ensuivre des e´quilibres de se´gre´gation comple`te, de se´gre´ga-tion incomple`te, ou d'inte´gration comple`te, selon les rentes relatives et les parame`tres deThe first author is also affiliated with National Taiwan University, while the second author is a research associate of NBER. We are grateful for valuable comments and suggestions from revenus, de pre´fe´rences ou de fiscalite´locale. Un e´quilibre de se´gre´gation peut entraıˆner une classification endoge`ne sur la base seulement des revenus ou sur la base des revenus et des pre´fe´rences. Alors que les riches n'ont pas besoin d'eˆtre plus proches du site du bien public local, des e´quilibres multiples peuvent surgir quand la configuration d'e´qui-libre en est une de se´gre´gation incomple`te.

No abstract